© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 128604
    Prev
    Next
    INDEX
    Explanations

    chemical compounds

    np_max-act · gemini-2.0-flash

    chemical compounds associated with safety concerns in the chemical industry.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron responds to numeric locants and hyphens in chemical names—that is, IUPAC‐style compound identifiers like “2,4,6-Trichloro-5-ethylpyrimidine.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bride
    -0.06
     앉
    -0.06
    awl
    -0.06
     gauss
    -0.06
     imagen
    -0.06
    uko
    -0.06
    Seat
    -0.06
    Ass
    -0.06
    ублі
    -0.06
    鱼
    -0.06
    POSITIVE LOGITS
     exhibiting
    0.07
    [v
    0.07
    』（
    0.07
    MITTED
    0.07
     Protected
    0.07
     Москва
    0.06
     Destructor
    0.06
     حل
    0.06
    .Migrations
    0.06
     shoulder
    0.06
    Activations Density 0.042%

    No Known Activations